The observation of human joint cartilage from x-ray, Computed Tomography (CT) or Magnetic Resonance Imaging (MRI) are the main diagnostic tools to evaluate pathologies or traumas. Our Database shows a set of novel measurements and 3D features based on MRI and CT data of the knee joint, used to reconstruct bone and cartilages and to assess cartilage condition from a new perspective.
Forty-seven subjects presenting a degenerative disease, a traumatic injury, or no symptoms or trauma were recruited in this study and scanned using CT and MRI. Using medical imaging software, the bone and cartilage of the knee joint were segmented, and 3D reconstructed. Several features such as cartilage density, presence of holes was extracted. An exhaustive evaluation made from the 2D images has also been performed. All the extracted features were used with advanced statistics tools and machine learning to test the ability of our model to predict cartilage conditions.
This work is a first step towards the development of a new gold standard of cartilage assessment based on 2D and 3D measurements.
Part of the data obtained from our work is now available on the Beta Version of chondral lesion database (clDB) containing a subgroup of the studied population.